Token导航 LogoToken导航

Agent Skill · 待分类

test-quality-inspector(测试质检员)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

test-quality-inspector 是待分类类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为权限未标注;许可证为 MIT,第三方扫描已通过,按安装量在待分类类的 11,209 个 Skill 里排第 1,249。

总安装 4,218周安装 174GitHub Stars 40下载 1,378核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:test-quality-inspector(测试质检员)
来源仓库:https://github.com/bobmatnyc/claude-mpm-skills
仓库路径:skills/test-quality-inspector
安装命令:
npx skills add https://github.com/bobmatnyc/claude-mpm-skills --skill test-quality-inspector
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/bobmatnyc/claude-mpm-skills --skill test-quality-inspector

这个 Skill 是做什么的

这个 Skill 的分类还没最终确定,用法以来源仓库的说明为准。

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。适合梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。不能把工具输出直接当最终结论,需先确认最小权限和操作边界。涉及密钥、令牌、用户数据或生产系统时,应先确认脱敏方式和权限。

安装方式:通过 npx skills add 命令从指定 GitHub 仓库添加。

来源仓库内路径:skills/test-quality-inspector

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/bobmatnyc/claude-mpm-skills --skill test-quali…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    权限没有明确标注,第一次使用时只给一个无关紧要的任务,观察它到底读了哪些文件和网络。

常见问题

6 条

test-quality-inspector 怎么安装?

在终端执行 npx skills add https://github.com/bobmatnyc/claude-mpm-skills --skill test-quality-inspect…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

test-quality-inspector 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

test-quality-inspector 需要什么权限?

权限级别没有明确标注。第一次使用时建议只给无关紧要的任务,观察它实际读写了哪些内容。

test-quality-inspector 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

test-quality-inspector 用的人多吗?

公开数据是累计安装 4,218 次,近一周安装 174 次,下载 1,378 次,GitHub 40 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

test-quality-inspector 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理待分类类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

待分类类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
infsh-cli

infsh CLI · Codex、Claude

4,374,576382权限未标注未明确未收录
ai-video-generation

AI 视频生成 · Codex、Claude

4,313,376382调用外部服务未明确有提醒
lark-openapi-explorer

云雀 OpenAPI 浏览器 · Codex、Claude

2,064,1209,011需要联网未明确有提醒
lark-workflow-standup-report

Lark 工作流程站立报告 · Codex、Claude

2,041,6328,978需要联网未明确通过
use-my-browser

使用我的浏览器 · Codex、Claude

1,848,49140操作浏览器未明确未通过
test-quality-inspector

测试质检员 · 本页

4,21840权限未标注MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Example Test Inspection Report

Scenario: User Registration Feature

Engineer's Test Suite

# test_user_registration.py

def test_user_creation():
    """Test user creation"""
    user = create_user("test@example.com", "password123")
    assert user

def test_login():
    """Test login"""
    user = create_user("test@example.com", "password123")
    result = login("test@example.com", "password123")
    assert result

def test_duplicate_email():
    """Test duplicate email"""
    create_user("test@example.com", "password123")
    user2 = create_user("test@example.com", "password456")
    assert user2

QA Inspection Report

Test 1: test_user_creation()

Claimed Intent: Test user creation Actually Tests: Object instantiation only

Issues Found

🔴 CRITICAL: Worthless Assertion

assert user  # Line 5
  • Would pass with corrupt data
  • Would pass with wrong email
  • Would pass with invalid password hash
  • Would pass if database save failed

Mental Debug: User object with garbage data would pass this test.

🟠 HIGH: Missing Validation Tests

  • No test for invalid email format
  • No test for weak password
  • No test for duplicate email (separate test exists but broken)
  • No test for SQL injection in email

🟠 HIGH: No Persistence Verification

  • Test doesn't verify user is saved to database
  • Test doesn't verify user can be retrieved
  • Transaction might be rolled back

🟡 MEDIUM: Vague Test Name

  • "test_user_creation" doesn't describe what should happen
  • Better: "test_user_creation_with_valid_data_persists_to_database"
Suggested Improvements
def test_user_creation_with_valid_data_persists_to_database():
    """Creating a user with valid email and password should:
    1. Create user object with correct attributes
    2. Save to database
    3. Hash password (not store plaintext)
    4. Set default role and active status
    """
    email = "test@example.com"
    password = "SecurePass123!"

    user = create_user(email, password)

    # Verify user object
    assert user.id is not None, "User should have an ID after creation"
    assert user.email == email, "Email should match input"
    assert user.is_active is True, "New users should be active by default"
    assert user.role == "user", "New users should have 'user' role"
    assert user.created_at is not None, "Created timestamp should be set"

    # Verify password is hashed, not plaintext
    assert user.password_hash != password, "Password should be hashed"
    assert len(user.password_hash) > 50, "Password hash should be substantial"

    # Verify persistence
    retrieved_user = User.get_by_email(email)
    assert retrieved_user is not None, "User should be retrievable from database"
    assert retrieved_user.id == user.id, "Retrieved user should match created user"

def test_user_creation_with_invalid_email_format_raises_validation_error():
    """Creating a user with malformed email should raise ValidationError"""
    invalid_emails = [
        "not-an-email",
        "@example.com",
        "test@",
        "test space@example.com",
        "",
    ]

    for invalid_email in invalid_emails:
        with pytest.raises(ValidationError) as exc:
            create_user(invalid_email, "password123")

        assert "email" in str(exc.value).lower()
        assert "invalid" in str(exc.value).lower()

def test_user_creation_with_weak_password_raises_validation_error():
    """Creating a user with weak password should raise ValidationError"""
    weak_passwords = [
        "123",          # Too short
        "password",     # No numbers
        "12345678",     # No letters
        "",             # Empty
    ]

    for weak_password in weak_passwords:
        with pytest.raises(ValidationError) as exc:
            create_user("test@example.com", weak_password)

        assert "password" in str(exc.value).lower()

Risk Level: 🔴 CRITICAL Action: ❌ BLOCK - Core functionality not tested Estimated Fix Time: 30 minutes


Test 2: test_login()

Claimed Intent: Test login Actually Tests: Function call completes

Issues Found

🔴 CRITICAL: Worthless Assertion

assert result  # Line 11
  • Passes with any truthy value
  • Doesn't verify session/token
  • Doesn't verify user authentication state

🔴 CRITICAL: Missing Negative Tests

  • No test for wrong password
  • No test for non-existent user
  • No test for locked account
  • No test for expired credentials

🟠 HIGH: No Session Verification

  • Doesn't verify authentication token
  • Doesn't verify session expiry
  • Doesn't verify user context in session

🟡 MEDIUM: Test Depends on Previous Test

  • Creates user in this test
  • Should use fixture or setup
  • Tests should be independent
Suggested Improvements
@pytest.fixture
def registered_user():
    """Fixture providing a registered user for login tests"""
    user = create_user("test@example.com", "SecurePass123!")
    yield user
    # Cleanup if needed
    User.delete(user.id)

def test_login_with_valid_credentials_returns_authenticated_session(registered_user):
    """Logging in with correct email and password should:
    1. Return authentication token/session
    2. Set authenticated state
    3. Include user context
    4. Set appropriate expiry
    """
    session = login(registered_user.email, "SecurePass123!")

    assert session is not None, "Login should return session"
    assert session.is_authenticated is True, "Session should be authenticated"
    assert session.user_id == registered_user.id, "Session should contain user ID"
    assert session.token is not None, "Session should have authentication token"
    assert session.expires_at > datetime.now(), "Session should have future expiry"
    assert (session.expires_at - datetime.now()).seconds >= 3600, "Session should last at least 1 hour"

def test_login_with_wrong_password_raises_authentication_error(registered_user):
    """Logging in with incorrect password should raise AuthenticationError"""
    with pytest.raises(AuthenticationError) as exc:
        login(registered_user.email, "WrongPassword")

    assert "Invalid credentials" in str(exc.value)
    assert "password" in str(exc.value).lower()

def test_login_with_nonexistent_email_raises_authentication_error():
    """Logging in with non-existent email should raise AuthenticationError"""
    with pytest.raises(AuthenticationError) as exc:
        login("doesnotexist@example.com", "password")

    assert "Invalid credentials" in str(exc.value)
    # Note: Don't reveal if email exists (security)

def test_login_with_locked_account_raises_account_locked_error(registered_user):
    """Logging in to locked account should raise AccountLockedError"""
    lock_account(registered_user.id)

    with pytest.raises(AccountLockedError) as exc:
        login(registered_user.email, "SecurePass123!")

    assert registered_user.email in str(exc.value)

def test_login_with_empty_password_raises_validation_error(registered_user):
    """Logging in with empty password should raise ValidationError"""
    with pytest.raises(ValidationError) as exc:
        login(registered_user.email, "")

    assert "password" in str(exc.value).lower()
    assert "required" in str(exc.value).lower()

Risk Level: 🔴 CRITICAL Action: ❌ BLOCK - Authentication not actually tested Estimated Fix Time: 45 minutes


Test 3: test_duplicate_email()

Claimed Intent: Test duplicate email handling Actually Tests: Second user creation succeeds (WRONG!)

Issues Found

🔴 CRITICAL: Test is Backwards

user2 = create_user("test@example.com", "password456")
assert user2  # Line 17
  • This test expects duplicate creation to SUCCEED
  • It should expect it to FAIL with an error
  • Test passes when it should fail
  • This is testing the opposite of what's needed

🔴 CRITICAL: False Confidence

  • Production bug: duplicate emails are allowed
  • Test claims to verify duplicate prevention
  • Test actually verifies duplicates work
  • QA might approve thinking it's covered

🟡 MEDIUM: Same Email Issue as Other Tests

  • If this fixed to expect error, needs all improvements from Test 1
Suggested Fix
def test_create_user_with_duplicate_email_raises_integrity_error():
    """Creating a user with an email that already exists should:
    1. Raise IntegrityError or ValidationError
    2. Not create duplicate user in database
    3. Preserve existing user data
    """
    email = "test@example.com"

    # Create first user
    user1 = create_user(email, "FirstPassword123!")
    initial_count = User.count()

    # Attempt to create duplicate
    with pytest.raises((IntegrityError, ValidationError)) as exc:
        create_user(email, "SecondPassword456!")

    assert "email" in str(exc.value).lower()
    assert "duplicate" in str(exc.value).lower() or "exists" in str(exc.value).lower()

    # Verify no new user created
    assert User.count() == initial_count, "User count should not increase"

    # Verify original user unchanged
    original_user = User.get_by_email(email)
    assert original_user.id == user1.id, "Original user should be intact"
    assert original_user.verify_password("FirstPassword123!"), "Original password should work"
    assert not original_user.verify_password("SecondPassword456!"), "New password should not work"

Risk Level: 🔴 CRITICAL Action: ❌ BLOCK - Test verifies opposite of requirement Estimated Fix Time: 20 minutes


Summary Report

Overall Assessment

Test Suite Quality: 🔴 FAILING

Critical Issues: 3

  • Test 1: Doesn't actually test user creation
  • Test 2: Doesn't actually test authentication
  • Test 3: Tests opposite of requirement

Total Tests: 3 Effective Tests: 0 Coverage: High (claims) Protection: None (reality)

Risk Assessment

Production Risk: 🔴 EXTREME

Current test suite provides zero protection against:

  • Data corruption in user creation
  • Authentication bypass
  • Duplicate email registration
  • Password security issues
  • Database integrity issues

Confidence Level: 0% - Tests passing means nothing

Required Actions

Immediate (Block Merge)
  1. Rewrite all three tests with proper assertions
  2. Add negative test cases (12+ tests needed)
  3. Verify tests catch intentional bugs
  4. Add fixture for test user management
Follow-up (Required for completion)
  1. Add edge case tests (15+ additional tests)
  2. Add integration tests for full registration flow
  3. Add security tests (SQL injection, XSS, etc.)
  4. Add performance tests for registration endpoint

Estimated Timeline

  • Fix critical issues: 2-3 hours
  • Complete test suite: 1 day
  • Review and iteration: 0.5 days

Total: 1.5-2 days for proper test coverage

Recommendation

❌ BLOCK MERGE

Do not approve this PR. Tests provide false confidence and mask critical bugs.

Evidence:

  • All tests would pass with completely broken functionality
  • Duplicate email test verifies the opposite of requirements
  • No actual behavior is verified

Next Steps:

  1. Engineer rewrites tests following examples above
  2. QA re-inspects rewritten tests
  3. QA verifies tests catch intentional bugs
  4. Only then approve merge

Lessons for Engineer

What Went Wrong

  1. Wrote tests after code - Led to tests that just confirm code runs
  2. Weak assertions - "assert x" proves nothing
  3. No mental debugging - Didn't verify tests catch bugs
  4. No negative testing - Only tested happy path
  5. Misunderstood duplicate test - Test verified opposite

How to Improve

  1. Write tests first (TDD) - Prevents these issues
  2. Specific assertions - Verify exact values
  3. Mental debugging - Break code, ensure test fails
  4. Test failures explicitly - Every success needs failure test
  5. Read test name carefully - Test what you claim to test

TDD Would Have Prevented This

If tests were written first:

# Write this FIRST (it will fail):
def test_user_creation_with_valid_data_persists_to_database():
    user = create_user("test@example.com", "password")
    assert user.email == "test@example.com"  # Will fail until create_user works
    ...

# Then implement create_user to make it pass

See the Test-Driven Development skill for complete TDD workflow (available in the skill library for comprehensive TDD guidance).


Sign-off

QA Inspector: [Your name] Date: [Date] Status: ❌ REJECTED Reason: Tests provide zero protection, must be rewritten Re-inspection Required: Yes


*This is what thorough test inspection looks like. Better to catch these issues now than in production.*

平台分布

Claude Code

31.21%
按下载量换算430

Antigravity

21.16%
按下载量换算292

Gemini CLI

16.87%
按下载量换算232

OpenCode

12.13%
按下载量换算167

Cursor

7.44%
按下载量换算103

windsurf

3.67%
按下载量换算51

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限未标注

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills